Symptom Based Health Status Prediction via Decision Tree, KNN, XGBoost, LDA, SVM, and Random Forest

Abstract

Machine learning applications in health science become more important and necessary every day. With the help of these systems, the load of the medical staff will be lessened and faults because of a missing point, or tiredness will decrease. It should not be forgotten that the last decision lies with the professionals, and these systems will only help in decision-making. Predicting diseases with the help of machine learning algorithm can lessen the load of the medical staff. This paper proposes a machine learning model that analyzes healthcare data from a variety of diseases and shows the result from the best resulting algorithm in the model. It is aimed to have a system that facilitates the diagnosis of diseases caused by the density of data in the health field by using these algorithms of previously diagnosed symptoms, thus resulting in doctors going a faster way while diagnosing the disease and have a prediction about the diseases of people who do not have the condition to go to the hospital. In this way, it can ease the burden on health systems. The disease outcome corresponding to the 11 symptoms found in the data set used is previously experienced results. During the study, different ML algorithms such as Decision Tree, Random Forest, KNN, XGBoost, SVM, LDA were tried and compatibility/performance comparisons were made on the dataset used. The results are presented in a table. As a result of these comparisons and evaluations, it was seen that Random Forest Algorithm gave the best performance. While data was being processed, input parameters were provided to each model, and disease was taken as output. Within this limited resource, our model has reached an accuracy rate of 98%.